llama-stack-mirror/llama_stack/providers/remote
Ashwin Bharambe 1463b79218
feat(registry): make the Stack query providers for model listing (#2862)
This flips #2823 and #2805 by making the Stack periodically query the
providers for models rather than the providers going behind the back and
calling "register" on to the registry themselves. This also adds support
for model listing for all other providers via `ModelRegistryHelper`.
Once this is done, we do not need to manually list or register models
via `run.yaml` and it will remove both noise and annoyance (setting
`INFERENCE_MODEL` environment variables, for example) from the new user
experience.

In addition, it adds a configuration variable `allowed_models` which can
be used to optionally restrict the set of models exposed from a
provider.
2025-07-24 10:39:53 -07:00
..
agents test: add unit test to ensure all config types are instantiable (#1601) 2025-03-12 22:29:58 -07:00
datasetio fix: allow default empty vars for conditionals (#2570) 2025-07-01 14:42:05 +02:00
eval refactor(env)!: enhanced environment variable substitution (#2490) 2025-06-26 08:20:08 +05:30
inference feat(registry): make the Stack query providers for model listing (#2862) 2025-07-24 10:39:53 -07:00
post_training fix: allow default empty vars for conditionals (#2570) 2025-07-01 14:42:05 +02:00
safety fix: sambanova shields and model validation (#2693) 2025-07-11 16:29:15 -04:00
tool_runtime fix: allow default empty vars for conditionals (#2570) 2025-07-01 14:42:05 +02:00
vector_io chore: Added openai compatible vector io endpoints for chromadb (#2489) 2025-07-23 13:51:58 -07:00
__init__.py impls -> inline, adapters -> remote (#381) 2024-11-06 14:54:05 -08:00